Efficient Brain Tumor Identification Based on Optimal Support Scaling Vector Feature Selection (OSSCV) Using Stochastic Spin-Glass Model Classification

Brain tumor detection is a developing defect finding task in medical imaging, as premature and early identification is a critical once for recommending early treatment. The tumor are identified by the laboratory through MRI images by finding the tumor regions. The Artificial intelligence play a vital role for finding, analyzing, the image data to attain the target results in medical image using
various learning methodologies. Most of the existing system failed to find the find the feature dimension leads poor accuracy for identifying tumor regions due to low precision, recall rate, lower intensity in image coverage region. To resolve this problem, to propose an Optimal Support Scaling Vector Based Feature Selection (OSSCV) brain tumor identification using Stochastic Spin-Glass Model
Classification (SSGM). Initially the preprocessing is done by bilateral filter and segmentation is applied by suing Active Region Slice Window Segmentation (ARSWS). To separate the tumor entity feature projection using Histogram color quantization and the features process are carried by Optimal Support Scaling Vector Based Feature Selection (OSSCV). The selected features get trained using Stochastic Spin-Glass Model Classification (SSGM) to find the tumor region. The proposed system outperforms traditional machine
learning methods in brain tumor detection. Finally proposed system of Stochastic Spin-Glass Model (SSGM) performance of recall is 95.5%, the performance of F1-score is 96.1% and the performance of the 96.5%. The proposed approach has the potential to assist radiologists in diagnosing brain tumors more accurately and efficiently, leading to improved patient outcomes.